> ## Documentation Index > Fetch the complete documentation index at: https://fal.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Quick Start > Get started with fal in minutes fal gives you two ways to work with AI models. If you want to generate images, video, audio, or other media, the [Model APIs](/documentation/model-apis/overview) let you call 1,000+ production-ready models with a single API call. If you have your own model to deploy, [Serverless](/documentation/serverless) gives you the full lifecycle: develop, test, deploy, and scale on the same infrastructure that powers the [marketplace](https://fal.ai/models). Both paths start with an [API key](/documentation/model-apis/authentication) and take a few minutes. The "consume" path is for calling existing models through fal's [client libraries](/documentation/model-apis/inference/client-setup) or HTTP. The "deploy" path is for teams bringing their own models to run on fal's GPU infrastructure, using the same [fal.App](/documentation/development/app-setup) framework that powers every model on the platform. ### What do you want to build? Create images from text prompts with FLUX, Nano Banana 2, and more Transform images into videos with Kling 3.0, Sora 2, and other models Convert speech to text with Whisper Build with Llama, Mistral, and other large language models Ultra-fast image generation with optimized FLUX Create interfaces for complex AI workflows Build full-stack AI apps with Next.js and fal Deploy AI-powered apps on Vercel with fal Automate workflows by connecting fal models to n8n ### Quick example Generate your first image in under a minute. ```bash Python theme={null} pip install fal-client ``` ```bash JavaScript theme={null} npm install @fal-ai/client ``` Get a key from the [fal dashboard](https://fal.ai/dashboard/keys) and set it as an environment variable: ```bash theme={null} export FAL_KEY="your-api-key-here" ``` ```python Python theme={null} import fal_client result = fal_client.subscribe("fal-ai/flux/schnell", arguments={ "prompt": "a futuristic cityscape at sunset" }) print(result["images"][0]["url"]) ``` ```javascript JavaScript theme={null} import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/flux/schnell", { input: { prompt: "a futuristic cityscape at sunset" } }); console.log(result.data.images[0].url); ``` ```bash cURL theme={null} curl -X POST "https://queue.fal.run/fal-ai/flux/schnell" \ -H "Authorization: Key $FAL_KEY" \ -H "Content-Type: application/json" \ -d '{"prompt": "a futuristic cityscape at sunset"}' ``` ### What do you want to deploy? Deploy Sana, FLUX, or your custom image generation model Deploy WAN or other video generation models Deploy Kokoro or custom voice synthesis models Deploy DiffRhythm or music generation models Run ComfyUI workflows as a serverless API Fine-tune WAN video generation with LoRA training Scale generation across multiple GPUs with streaming Stream real-time text-to-3D reconstruction Run real-time video-to-video with object detection Deploy a real-time world model powered by Matrix-Game Deploy any model with custom Docker containers ### Migrating from another platform? Move your Replicate models to fal Move your Modal apps to fal Move your RunPod Serverless workers to fal Move your existing Docker-based inference server to fal ### Quick example Deploy your first app in under 2 minutes. ```bash theme={null} pip install fal fal auth login ``` Create a file called `my_app.py`: ```python my_app.py theme={null} import fal class MyApp(fal.App): @fal.endpoint("/") def run(self, prompt: str) -> dict: return {"message": f"Hello from fal! You said: {prompt}"} ``` ```bash theme={null} fal run my_app.py::MyApp ``` ```bash theme={null} fal deploy my_app.py::MyApp ``` Step-by-step guide to deploying an image generation model *** ## Next Steps Create an API key to authenticate your requests Use AI coding assistants to build with fal faster Browse 1,000+ available models